arXiv CS
open access
CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty
Large language models (LLMs) are becoming prevalent in scenarios where honesty is critical. However, despite alignment training, these models still exhibit dishonest behaviour, such as outputting claims that contradict some knowledge or are not supported by what is accessible in context. We introduc
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty#1357947
- Representational alignment yields generalizable safety in language models#926872
- When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs#799185
- When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs#797762
- Damnatio Memoriae: Adversarially and Selectively Forgetting Identities in the Embedding Space of Face Recognition Models#1063326
Record · ID 1348841
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive